Introduction to Computational Thinking and Data Science
Python for computational problem solving: optimization, graphs, simulation, statistics, experimental data and an introduction to machine learning.
Computation can solve real problems in almost any field once you know how to model them. This continuation of an introductory Python programming course shows how, in 15 recorded lectures with notes: optimization problems, graph-theoretic models, stochastic thinking, random walks and Monte Carlo simulation, confidence intervals and sampling, understanding experimental data, and an introduction to machine learning with clustering and classification, ending with common statistical mistakes.
What You Will Achieve
- Model optimization problems and solve them with Python programs
- Represent problems as graphs, such as finding the fastest route across a campus
- Build random walk and Monte Carlo simulations and estimate confidence intervals
- Apply clustering and classification to data while avoiding common statistical errors
Program Overview
Optimization and Graphs
Modeling problems so a program can solve them.
- Optimization problems
- Graph-theoretic models
Stochastic Thinking and Simulation
Randomness, simulation and how far to trust results.
- Stochastic thinking and random walks
- Monte Carlo simulation
- Confidence intervals, sampling and standard error
- Understanding experimental data
Machine Learning and Statistical Sins
Learning from data, and the ways it goes wrong.
- Introduction to machine learning
- Clustering
- Classification
- Statistical sins
Course Completion
Job Outlook
Computational modeling and data analysis in Python are used in data science, scientific research, engineering, finance and operations analysis.
Good for: Learners who can write basic Python and want to use it to model problems, run simulations and analyze data.
Keep in mind: The five programming problem sets have no published solutions; the lectures follow John Guttag’s Introduction to Computation and Programming Using Python, second edition.
Bottom line: A well-taught second course in Python that turns programming into a tool for modeling and data science.
Frequently Asked Questions
What are the programming problem sets about?
Five Python projects: transporting space cows, finding the fastest way to get around MIT, a robot simulation, simulating the spread of disease and bacteria, and modeling global warming from data.
How does it relate to 6.0001?
It is the second half of a two-part sequence: 6.0001 covers the first half of the term and this course the second, and together they match the full-term 6.00 course.
What are statistical sins?
The closing lectures cover common ways data analysis misleads, as a counterpoint to the machine learning and statistics techniques taught earlier in the course.



There are no reviews yet.